Cephalonauts One: A deep fMRI dataset for decoding naturalistic speech in the human brain
cs.LG, cs.AI
Submitted: 2026-10-02
Updated: 2026-10-02
Comments: Accepted at NeurIPS 2026, Evaluations & Datasets Track
License: http://creativecommons.org/licenses/by/4.0/
The gist: Cephalonauts One is a whole-brain 3 Tesla (3T) functional magnetic resonance imaging (fMRI) dataset recorded while subjects listened to audio podcasts.
Abstract
Cephalonauts One is a whole-brain 3 Tesla (3T) functional magnetic resonance imaging (fMRI) dataset recorded while subjects listened to audio podcasts. Three healthy subjects underwent multiple scanning sessions, each consisting of five 15-minute runs, while listening to podcasts in their native language. With 30 hours of fMRI data per subject, the current release is the deepest available fMRI dataset using naturalistic speech stimuli. The dataset pairs brain activity with the corresponding podcast audio, transcript annotations, and derived stimulus embeddings. Furthermore, we introduce a brain decoding benchmark formulated as audio segment retrieval: given fMRI activity from a held-out session, the decoder must identify the corresponding time-aligned podcast audio segment among candidate segments. We provide standardized splits, evaluation metrics, and baseline decoders for this task. Finally, a scaling analysis shows that decoding performance improves continuously with the amount of training data per subject.
Sources
- MAEB: Massive Audio Embedding Benchmark
- Scaling laws for decoding images from brain activity
- Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding
- Gemini: A Family of Highly Capable Multimodal Models
- The Algonauts Project 2025 Challenge: How the Human Brain Makes Sense of Multimodal Movies
- Optimizing fMRI Data Acquisition for Decoding Natural Speech with Limited Participants
- Scaling Laws for Neural Language Models
- Universal-2-TF: Robust All-Neural Text Formatting for ASR
- Adam: A Method for Stochastic Optimization
- Decoupled Weight Decay Regularization
- Natural scene reconstruction from fMRI signals using generative latent diffusion
- LibriBrain: Over 50 Hours of Within-Subject MEG to Improve Speech Decoding Methods at Scale
- Learning Transferable Visual Models From Natural Language Supervision
- Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks